Manjula Gururaj H

Dr. Manjula Gururaj H

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2019
Verified
Conference Paper
Closed access
MHManjula Gururaj H
Manjula Gururaj H
GNG. S Nagaraja
G. S Nagaraja
To detection of any types of anomalies in the medical images, the quality of the image is very important. To improve the quality of the images pre-processing steps are used. This includes the image enhancement and noise removal. Removing of the noise is done by various methods. This paper elaborates on different types of noise in the X-ray Dicom images and different filtering methods. Image improvement is calculated using PSNR and MSE.

22 December 2022
Verified
Conference Paper
Closed access
MHManjula Gururaj H
Manjula Gururaj H
KPKarthik P
Karthik P
KKKishan R Kotian
Kishan R Kotian
DHDhanush P Hegde
Dhanush P Hegde
Health is important for all living beings. The prevention of any disease is always better. Some of the diseases, like heart attack and stroke, can be prevented. The majority of strokes are caused by an unexpected blockage of pathways in the heart and brain. One of the deadliest disorders is brain stroke and now is a typical occurrence. The effects of a stroke could be fatality, severe disability, or permanent brain damage. Stroke requires immediate medical treatment. The severity of a stroke can be lessened by early recognition of numerous stroke warning symptoms. Due to this, a lower death rate can be achieved. In this research, the data collected from the patients/subjects is divided into the dependent variable and the non-dependent variable. These dependent and non-dependent variables are clustered and applied with the different machine learning algorithms such as Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Light GBM (LGBM) and XG Boost (XGB). Along with this, the model is developed to predict the best result. The model that was created is compared to all of the other models, and the results are discussed.

22 December 2022
Verified
Conference Paper
Closed access
MHManjula Gururaj H
Manjula Gururaj H
GGGagan G
Gagan G
NCNikhil T C
Nikhil T C
APA B Pradeep
A B Pradeep
A variety of applications, including automated toll collection, traffic law enforcement, security monitoring of restricted locations, and unattended parking lots, rely on license plate recognition (LPR) or Vehicle Number Plate (VNP). LPR methods differ depending on the application due to various operating circumstances. It is imperative that the vehicle has permission to enter the grounds in a number of public settings, including hospitals, airports, schools, and universities. There are restrictions on automotive admission to specific regions in some public venues, such as hospitals, universities, community centers. Parking vehicles in approved spots really does matter in public areas. In university and collages the number of the vehicles usage and intake is more. The allotting the slots to them during the peak hour and authorizing the vehicle is very much difficult and it is tedious job. Automated license plate detection (ANP/AVNP), which frees us up to focus on parking the vehicle while simultaneously verifying its authenticity, is a solution we propose to prevent such situations. The proposed model first pre-processes the images and later segments the image before identifying and classifying the vehicle. Based on the categorization, the parking place will be allotted to the particular car. In order to segment characters, the bounding box method and blob detection are used. The character is then identified using OCR (Optical Character Recognition). After the VNP has been found and identified, it is checked in the main database to see if entrance into the Campus has been granted. If VNP is the visitor, then the slot will be assigned daily.

12 December 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
KRK. Hemant Kumar REDDY
K. Hemant Kumar REDDY
MHManjula Gururaj H
Manjula Gururaj H
NPNIHAR RANJAN PRADHAN
NIHAR RANJAN PRADHAN
DRDiptendu Sinha Roy
Diptendu Sinha Roy
The necessity to address the growing pace of industrialization and resource constraints has underscored the importance of developing innovative Information and Communication Technology solutions. The prevailing “smart industry” paradigm is distinguished by its widespread cyber infrastructure for monitoring and controlling critical industrial assets. In case sudden failure of any equipment shot down the industry and apart from financial loss, it take ample amount of time to recover. To effectively manage the multitude of continuous services while maintaining their quality of service requirements, it is crucial to concurrently utilize sensor-based real-time assessment for predicting employed equipment status and lifespan become a challenging. This research explores the feasibility of enhancing the lifespan of sensors at the fog layer by implementing intelligent sleep and wake-up duty cycles. We propose a clustered-based duty-cycling approach that optimizes service continuity with a minimal number of active sensor nodes using a genetic algorithm. The abovementioned framework simulated in iFogSim simulator and obtained results demonstrate the reduced the energy consumption by approximately 16% to 20% over the energy efficient aware and around 38% to 42% over the K-mean clustering approach with 90% duty cycle.

21 December 2022
Verified
Conference Paper
Closed access
MHManjula Gururaj H
Manjula Gururaj H
SPSumathi Pawar
Sumathi Pawar
PHPriyanka H
Priyanka H
KRK Hemant Kumar Reddy
K Hemant Kumar Reddy
A smart city is a trend in urban planning that uses technology for communication and information to enhance nearly every element of urban life. In a smart city, inhabitants can communicate directly with each other and the infrastructure at any time. Due to the widespread use of smart devices, security and privacy concerns have grown into a serious problem that calls for strong solutions. The system is secured via biometrics, OTP creation, iris detection, and other security-related techniques. The biometric system is one of the more well-established security solutions. Obtaining images with near-infrared (NIR) or visible wavelength (VW) lighting under constrained and unconstrained conditions is the primary challenge with biometric security systems. This paper proposes a model for having secured access to amenities in smart cities. The model will use a combination of biometric features to provide access to ITS services. This includes the combinations of iris, periocular, and fingerprints. The proposed model elaborates on the level 3 type of authentication system and the amalgamation of iris, periocular, and fingerprint features for authentication. The suggested model operates on the concepts of data augmentation, feature learning with CNN, and deep learning for the detection of biometric authentication.

22 December 2022
Verified
Conference Paper
Closed access
MHManjula Gururaj H
Manjula Gururaj H
KRK Hemant Kumar Reddy
K Hemant Kumar Reddy
AAAshoor Ahamed
Ashoor Ahamed
ASAyushi Shetty
Ayushi Shetty
Numerous applications, such as automated toll collection, traffic law enforcement, security monitoring of restricted areas, and unattended parking lots, depend on license plate recognition (LPR). LPR techniques vary based on the application due to varying operating conditions. In various public sectors, including hospitals, airports, schools, and universities, permission for the vehicle to access the premises is absolutely essential. Some public spaces, including hospitals, community centers, and other places, have automobile entry restrictions to certain areas. In some cases, parking vehicles in designated spaces matters a lot in public places. In hospitals, patients' lives are more important, and emergency situations must be taken into mind. In hospitals, patients' lives matter more and emergencies must be taken into account. On occasion, traffic on hospital grounds might cause kayos, making it difficult to park vehicle in the designated lots. To prevent such occurrences, we suggest automated license plate detection, which allows us to concentrate on parking the vehicle while also confirming its authenticity. The suggested model begins by segmenting the image, then identifies and categorizes the vehicle. The parking space will be assigned to the specific vehicle based on the categorization. Character recognition is accomplished using the bounding box technique, whereas classification and detection are accomplished using a multimodal. The results and the accuracy of the multimodal is discussed.